"Understanding MCP for IDA" matching MCP servers:

Enables large language models to read and write IDA Pro databases through structured tool calls for reverse engineering, binary analysis, and hook development. Provides broker-based routing, SQLite-backed static caching, multi-instance analysis, and both cached and live IDA API queries.

Enables MCP clients to drive IDA Pro through a stability-hardened server that hosts multiple headless idalib instances, with per-session isolation, configurable HTTP/stdio transports, and API-key authentication.

Deterministic, local-first MCP server for IDA Pro and IDA Home, exposing 109 strict-schema operations for reverse engineering with policy-gated mutations, evidence tracking, and broad AI-client support.

Enables AI clients such as Claude, Cursor, Cline, and Codex to remotely drive IDA Pro over HTTP through 88 tools, covering Hex-Rays decompilation, disassembly, cross-reference tracing, type and struct reconstruction, C header import, memory reading and patching, and full dynamic debugging with breakpoints, registers, and stepping.

Extends IDA Pro with multi-instance support and vulnerability scanning for AI-assisted reverse engineering.

Enables AI assistants to autonomously inspect and control IDA Pro via MCP, providing tools for decompilation, disassembly, cross-references, renaming, typing, patching, searching, debugging, and arbitrary IDAPython execution.

An enhanced MCP server for IDA Pro that integrates bulk binary export, multi-instance management via Broker mode, and 80+ analysis tools for AI-assisted reverse engineering.

Enables LLMs to perform binary analysis and reverse engineering via IDA Pro's headless idalib, providing 66 MCP tools like decompile, disasm, and xrefs without requiring the IDA GUI.

Enables any MCP-capable AI to headlessly launch and dynamically instrument Windows executables via IDA Pro's PIN tracer, with tools for breakpoints, register/memory access, execution control, and instruction tracing without opening the IDA GUI.

Enables LLMs to perform automated penetration testing and Active Directory reconnaissance through Mythic, with tools for executing PowerShell, AD recon, domain user enumeration, and Kerberoasting.

Scans MCP servers for security vulnerabilities, prompt injection, and tool poisoning, providing risk scores and protection.

Headless reverse engineering MCP server integrating IDA Pro for static analysis and x64dbg for dynamic debugging via controlled MCP tools.

Headless MCP server for IDA Pro enabling on-demand database loading and programmatic reverse engineering workflows via MCP tools.

Enables AI agents to control a local Chromium browser via CDP for page snapshots, screenshots, human-like interactions, autonomous crawling, API/GraphQL reconnaissance, authenticated differential testing, and Burp-like intercept, repeater, and intruder workflows with scope enforcement and audit logging.

MCP server for the pwncat post-exploitation platform. It exposes 40+ tools for session management, file operations, command execution, enumeration, privilege escalation, implants, and config to AI agents.

Enables Android APK static analysis in Cursor/Claude via GDA CLI Server, supporting reconnaissance, attack surface scanning, and code decompilation through natural language.

Enables IDA Pro to run as a persistent, multi-agent analysis service with background jobs, allowing clients to submit binaries and query results without keeping the session open.

MCP server for .onion/dark web research that exposes the OpenTor skill engine over Model Context Protocol, enabling authorized threat intelligence, red teaming, and security research from any MCP-compatible client.

An intentionally vulnerable MCP server designed as a live demo target for the MCP Trust security scanner. It contains deliberate insecure patterns to demonstrate scanning capabilities.

GDB Enhanced Features MCP server for remote debugging and CTF exploitation with 41 specialized tools including ROP search, format-string detection, and memory patching.